Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ambient-code/platform/gerrit-reviewnpx skills add ambient-code/platform --skill gerrit-reviewgit clone --depth 1 https://github.com/ambient-code/platformWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00062 | $0.00797 |
| Opus 5 | $0.00031 | $0.00398 |
| Sonnet 5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
gerrit-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- gerrit-review — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gerrit Code Review
Guide for reviewing changes on a Gerrit instance using the Gerrit MCP server tools.
Prerequisites
The Gerrit MCP server must be available (credentials configured via Integrations page). If mcp__gerrit__* tools are not listed, the user needs to connect their Gerrit instance first.
Workflow
1. Fetch the change
Use mcp__gerrit__fetch_gerrit_change with the change ID (numeric or change-Id).
Extract from the response:
- Subject and commit message — understand what the change does
- Owner — who authored it
- Status — NEW (open), MERGED, ABANDONED
- Current patch set number — the latest revision
- Files changed — list of modified files with insertions/deletions
- Existing comments — what reviewers have already said
- Labels — current votes (Code-Review, Verified, etc.)
2. Read the diffs
Use mcp__gerrit__fetch_patchset_diff to compare patch sets or view the current diff.
- To see the full change: compare patch set 1 vs current (or base vs current)
- To see what changed between review rounds: compare two specific patch sets
- Filter by file path if the change is large — focus on the most impactful files first
3. Analyze and form review feedback
Apply standard code review principles:
- Correctness — does the logic do what the commit message claims?
- Edge cases — missing null checks, boundary conditions, error handling
- Style — follows project conventions (check CLAUDE.md if available)
- Security — no credentials in code, proper input validation, no injection vectors
- Performance — unnecessary allocations, N+1 queries, missing caching
4. Post the review
Use mcp__gerrit__submit_gerrit_review to post feedback:
- message: A summary of your review findings (top-level comment)
- labels: Vote appropriately:
Code-Review +1— looks good but someone else should also reviewCode-Review +2— approved, ready to submit (only if you have authority)Code-Review -1— needs changes before mergingCode-Review -2— blocks submission (serious issues)Verified +1— tests pass, builds clean
- comments: Inline comments on specific files and lines
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 71 lines · 62 tokens per session scan A 3efc5a92ad43
gerrit-review is a skill published in the GitHub repository ambient-code/platform (129 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 797 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…